BroadRouter

LLM API pricing by provider

Updated

We track 41 LLM API providers, 1,671 prices in all, each read from the provider's own pricing page (newest check 2026-11-15). Amazon Bedrock lists the most models (108). DeepInfra is the cheapest host for the most shared models (37). 9 providers publish batch prices and 35 publish cached-input prices.

Each provider page has its full price list with source links, the models it is the cheapest host for, its service tiers and how its prices compare with each model maker's own API. Pages for providers with fewer than 3 models are listed but kept out of search results, unless at least 2 of their models are also priced by another provider. BroadRouter is BroadNet's own site; BroadNet Inference is listed last and not ranked.

LLM API providers with model counts, cheapest model and tiers
ProviderModelsCheapest model (input / output per 1M)Tiers publishedCheapest forChecked
Amazon Bedrock host108Voxtral Mini 1.0 USD 0.04 / USD 0.04cached, batch, flex / spot, priority, fast7 of 68 (1 tied)2026-11-15
Azure OpenAI and Foundry Models host97NVIDIA Nemotron 3.5 Lightning 30B A3B USD 0.06 / USD 0.22cached, batch, flex / spot, priority, fast0 of 532026-11-14
GMI Cloud host97DeepSeek V4 Flash USD 0.091 / USD 0.182cached23 of 91 (5 tied)2026-11-15
DeepInfra host92Llama 3.1 8B Instruct USD 0.02 / USD 0.04cached, flex / spot, priority37 of 81 (9 tied)2026-11-14
Featherless host87Gemma 3 4B USD 0.05 / USD 0.10cached13 of 86 (5 tied)2026-11-15
Novita AI host67Llama 3.1 8B Instruct USD 0.02 / USD 0.05cached, fast6 of 582026-11-14
Vertex AI host63GPT OSS 20B USD 0.07 / USD 0.25cached, batch, priority3 of 542026-11-14
DigitalOcean Gradient host59GPT-5 Nano USD 0.05 / USD 0.40cached, flex / spot, fast0 of 572026-11-14
Venice host57Qwen 2.5 7B USD 0.05 / USD 0.13cached, fast, ultrafast2 of 452026-11-15
SiliconFlow host56Qwen 2.5 7B USD 0.05 / USD 0.05cached11 of 472026-11-15
Alibaba Cloud Model Studio maker42Qwen3.7 Flash USD 0.03 / USD 0.13cached, fast1 of 26 (1 tied)2026-11-14
Cloudflare Workers AI host40Granite 4.0 H Micro USD 0.017 / USD 0.112cached4 of 29 (1 tied)2026-11-14
Parasail host39GPT OSS 20B USD 0.04 / USD 0.20cached, fast1 of 332026-11-14
OpenAI maker37GPT-5 Nano USD 0.05 / USD 0.40cached, batch, flex / spot, fast, ultrafast27 of 27 (27 tied)2026-11-14
Together AI host25Rnj-1 Instruct USD 0.15 / USD 0.15cached1 of 212026-11-14
Perplexity maker24Claude Haiku 5.5 USD 0.10 / USD 0.50cached0 of 222026-11-15
Z.ai maker21GLM-4-32B-0414-128K USD 0.10 / USD 0.10cached4 of 12 (4 tied)2026-11-14
CoreWeave Forge (formerly W&B Inference) host20GPT OSS 20B USD 0.03 / USD 0.13cached7 of 202026-11-15
Anthropic maker18Claude Haiku 5.5 USD 0.10 / USD 0.50cached, batch, fast15 of 15 (15 tied)2026-11-14
Chutes host18gemma-4-31B-it-turbo USD 0.12 / USD 0.37cached, fast8 of 18 (1 tied)2026-11-15
Fireworks AI host15NVIDIA Nemotron 3.5 Lightning 30B A3B USD 0.05 / USD 0.20cached, flex / spot, priority, fast0 of 132026-11-14
Baidu maker14DeepSeek V4 Flash USD 0.14 / USD 0.28cached, fast1 of 11 (1 tied)2026-11-15
Baseten host14DeepSeek V4 Flash 0731 USD 0.13 / USD 0.26cached, fast2 of 14 (2 tied)2026-11-14
Gemini API maker12Gemini 2.5 Flash-Lite USD 0.10 / USD 0.40cached, batch, flex / spot, priority11 of 11 (11 tied)2026-11-14
Hyperbolic host11DeepSeek V4 Flash 0731 USD 0.06 / USD 0.18cached0 of 112026-11-14
Crusoe Cloud host9NVIDIA Nemotron 3.5 Lightning 30B A3B USD 0.05 / USD 0.20cached1 of 82026-11-15
IBM watsonx.ai maker9Granite 4.0 H Small USD 0.0636 / USD 0.265standard only0 of 72026-11-15
Mistral AI maker9Ministral 3 3B USD 0.10 / USD 0.10cached, batch, priority3 of 6 (3 tied)2026-11-15
xAI maker8Grok Build 0.1 USD 1 / USD 2cached6 of 6 (6 tied)2026-11-14
AkashML host7GPT OSS 20B USD 0.018 / USD 0.09cached1 of 72026-11-15
Amazon Nova on Bedrock maker7Nova Micro 1.0 USD 0.035 / USD 0.14batch, flex / spot, priority, fast—2026-11-15
Cohere maker6Command R7B (12-2024) USD 0.0375 / USD 0.15standard only1 of 12026-11-14
FriendliAI host5Gemma 4 31B USD 0.14 / USD 0.40cached0 of 52026-11-15
SambaNova Cloud host5OpenAI GPT OSS 120B USD 0.22 / USD 0.59cached0 of 52026-11-14
Groq host4GPT OSS 20B USD 0.075 / USD 0.30cached0 of 42026-11-14
Moonshot AI (Kimi) maker4Kimi K2.6 USD 0.95 / USD 4cached, batch, fast0 of 42026-11-14
Nscale host4Qwen3.8-Flash-Next-FP8 USD 0.15 / USD 0.47standard only0 of 32026-11-15
AI21 Labs maker2Jamba Mini 2 USD 0.20 / USD 0.40standard only—2026-11-15
Cerebras host2OpenAI GPT OSS 120B USD 0.35 / USD 0.75standard only0 of 22026-11-14
DeepSeek maker2DeepSeek V4.1 Flash 1017 USD 0.30 / USD 1.20cached0 of 22026-11-14
MiniMax maker2MiniMax M3.1 Flash USD 0.15 / USD 0.60cached, priority1 of 2 (1 tied)2026-11-14
BroadNet Inference this site's owner, not ranked4See BroadNet pricingper token, hourly key, flat plans—rate card

"Models": distinct models with a standard per-token price. "Cheapest model": lowest standard price on a blend of 3 input to 1 output token. "Cheapest for": models where the provider has the lowest standard price, out of the models it shares with at least one other provider; "tied" counts models where another provider charges the same (a maker's own API is listed first on a tie). Tiers: cached input, batch, flex or spot, priority and fast, where the provider publishes a per-model price.

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

All models: API prices compared · Cheapest LLM APIs right now · Download every price (CSV, JSON)

Questions

Which LLM API provider is the cheapest?

No single provider is cheapest for every model. Counting models with standard prices from two or more providers, DeepInfra is cheapest for 37, OpenAI is cheapest for 27 and GMI Cloud is cheapest for 23. Each provider page lists the models it wins and by how much, on a blend of 3 input tokens to 1 output token.

Which providers offer batch pricing per model?

Amazon Bedrock, Azure OpenAI and Foundry Models, Vertex AI, OpenAI, Anthropic, Gemini API, Mistral AI, Amazon Nova on Bedrock and Moonshot AI (Kimi) publish a batch price per model. Others, such as Novita AI, DigitalOcean Gradient, Alibaba Cloud Model Studio and Together AI, describe batch only as a blanket discount or not per model, so we list no batch rows for them.

Which providers publish cached-input prices?

35 of 41: Amazon Bedrock, Azure OpenAI and Foundry Models, GMI Cloud, DeepInfra, Featherless, Novita AI, Vertex AI, DigitalOcean Gradient, Venice, SiliconFlow, Alibaba Cloud Model Studio, Cloudflare Workers AI, Parasail, OpenAI, Together AI, Perplexity, Z.ai, CoreWeave Forge (formerly W&B Inference), Anthropic, Chutes, Fireworks AI, Baidu, Baseten, Gemini API, Hyperbolic, Crusoe Cloud, Mistral AI, xAI, AkashML, FriendliAI, SambaNova Cloud, Groq, Moonshot AI (Kimi), DeepSeek and MiniMax. IBM watsonx.ai, Amazon Nova on Bedrock, Cohere, Nscale, AI21 Labs and Cerebras show no cache price on the pages we read, so cached tokens bill at the input price there.

Which providers have priority or flex tiers?

Priority: Amazon Bedrock, Azure OpenAI and Foundry Models, DeepInfra, Vertex AI, Fireworks AI, Gemini API, Mistral AI, Amazon Nova on Bedrock and MiniMax. Flex or spot: Amazon Bedrock, Azure OpenAI and Foundry Models, DeepInfra, DigitalOcean Gradient, OpenAI, Fireworks AI, Gemini API and Amazon Nova on Bedrock. Priority costs more for reliability; flex and spot cost less but can be slow or refused at capacity.

Where do these prices come from?

From each provider's own pricing page or model pages, read with AI assistance and a page renderer, with the URL, check date and a quote stored for every price. No aggregator feed is used. 16 of the 41 providers are model makers selling their own models (some also host others); the rest are hosts.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity

Sources